Nan Lu
10 papers · 2019–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Conference Polyglot (5) π£ Hot Topic Early Bird π Cross-Pollinator (14) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13)
π§
Keyword Pioneer
π
Keyword Champion
(2)
π₯
Unstoppable
(5)
Conferences
ACML (2)
ICLR (2)
ICML (2)
NIPS (2)
ACL (1)
AISTATS (1)
Top co-authors
Keywords
semi-supervised learning
(3)
domain adaptation
(3)
importance weighting
(3)
weakly supervised learning
(2)
empirical risk minimization
(2)
distribution shift
(2)
binary classification
(2)
class prior
(2)
unlabeled datum
(2)
model generalization
(1)
overfitting mitigation
(1)
density ratio
(1)
text-to-speech synthesis
(1)
upper bound
(1)
risk consistency
(1)
unbiased risk estimator
(1)
noisy-label learning
(1)
duration control
(1)
zero-shot text-to-speech
(1)
risk estimator
(1)
Papers
TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis
ACL 2026
Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems
NIPS 2023
Federated Learning from Only Unlabeled Data with Class-conditional-sharing Clients
ICLR 2022
Multi-class Classification from Multiple Unlabeled
Datasets with Partial Risk Regularization
ACML 2022
Pointwise Binary Classification with Pairwise Confidence Comparisons
ICML 2021
Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
ICML 2021
Rethinking Importance Weighting for Deep Learning under Distribution Shift
NIPS 2020
A One-step Approach to Covariate Shift Adaptation
ACML 2020
Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
AISTATS 2020
On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
ICLR 2019